© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-65K
    7. 2112
    Prev
    Next
    INDEX
    Explanations

    complex emotions and thoughts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     פור
    0.73
     excelencia
    0.71
     التكامل
    0.71
     बदनाम
    0.66
     tragedia
    0.62
     örnek
    0.61
     운영
    0.61
     przykład
    0.61
    災
    0.60
     crackdown
    0.60
    POSITIVE LOGITS
     feelings
    3.06
     emotions
    2.69
     Feelings
    2.53
     thoughts
    2.51
     sentimientos
    2.21
     sentiments
    2.18
     feeling
    2.18
     emotion
    2.10
     desires
    2.09
     Emotions
    2.05
    Activations Density 2.069%

    No Known Activations